• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
  • HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI

    Team reports 99.9% Sudoku-Extreme accuracy with fewer than 250,000 parameters

    The team says adding persistent memory and removing timestep conditioning turned a denoising model into an iterative solver.

    EN
    1 Source, 19d ago, first seen 19d ago

    TLDR

    The team reports 99.9% accuracy on Sudoku-Extreme and 98.3% on Maze-Unique with a model containing fewer than 250,000 parameters. It describes the modified denoising model as an “anytime iterative solver.” A team member says retaining memory between steps “seems key,” drawing a parallel with classic Sudoku solvers using memory to track possible states.

    Combined views

    7.6K

    1 Source, first seen 19d ago

    Combined views

    7.6K

    1 Source, first seen 19d ago

    67 likes
    67 likes
    2 comments
    57 saves
    6 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    2 comments
    57 saves
    6 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    1 Source

    @eyvindnbrilliant work from our team! led by @MariiaD_ML+@aidan_sirbu, we explore reasoning w/ somewhat atypical diffusion models. classic sudoku solvers need memory to track possible states -> providing denoisers w/ persistent memory between steps seems key! 99.9% on sudoku extreme 🤯

    1 Source

    @eyvindnbrilliant work from our team! led by @MariiaD_ML+@aidan_sirbu, we explore reasoning w/ somewhat atypical diffusion models. classic sudoku solvers need memory to track possible states -> providing denoisers w/ persistent memory between steps seems key! 99.9% on sudoku extreme 🤯